![Daniel Borkmann](/assets/img/avatar_default.png)
This patch adds necessary infrastructure to the congestion control framework for later per route congestion control support. For a per route congestion control possibility, our aim is to store a unique u32 key identifier into dst metrics, which can then be mapped into a tcp_congestion_ops struct. We argue that having a RTAX key entry is the most simple, generic and easy way to manage, and also keeps the memory footprint of dst entries lower on 64 bit than with storing a pointer directly, for example. Having a unique key id also allows for decoupling actual TCP congestion control module management from the FIB layer, i.e. we don't have to care about expensive module refcounting inside the FIB at this point. We first thought of using an IDR store for the realization, which takes over dynamic assignment of unused key space and also performs the key to pointer mapping in RCU. While doing so, we stumbled upon the issue that due to the nature of dynamic key distribution, it just so happens, arguably in very rare occasions, that excessive module loads and unloads can lead to a possible reuse of previously used key space. Thus, previously stale keys in the dst metric are now being reassigned to a different congestion control algorithm, which might lead to unexpected behaviour. One way to resolve this would have been to walk FIBs on the actually rare occasion of a module unload and reset the metric keys for each FIB in each netns, but that's just very costly. Therefore, we argue a better solution is to reuse the unique congestion control algorithm name member and map that into u32 key space through jhash. For that, we split the flags attribute (as it currently uses 2 bits only anyway) into two u32 attributes, flags and key, so that we can keep the cacheline boundary of 2 cachelines on x86_64 and cache the precalculated key at registration time for the fast path. On average we might expect 2 - 4 modules being loaded worst case perhaps 15, so a key collision possibility is extremely low, and guaranteed collision-free on LE/BE for all in-tree modules. Overall this results in much simpler code, and all without the overhead of an IDR. Due to the deterministic nature, modules can now be unloaded, the congestion control algorithm for a specific but unloaded key will fall back to the default one, and on module reload time it will switch back to the expected algorithm transparently. Joint work with Florian Westphal. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
425 lines
10 KiB
C
425 lines
10 KiB
C
/*
|
|
* Pluggable TCP congestion control support and newReno
|
|
* congestion control.
|
|
* Based on ideas from I/O scheduler support and Web100.
|
|
*
|
|
* Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org>
|
|
*/
|
|
|
|
#define pr_fmt(fmt) "TCP: " fmt
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/types.h>
|
|
#include <linux/list.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/jhash.h>
|
|
#include <net/tcp.h>
|
|
|
|
static DEFINE_SPINLOCK(tcp_cong_list_lock);
|
|
static LIST_HEAD(tcp_cong_list);
|
|
|
|
/* Simple linear search, don't expect many entries! */
|
|
static struct tcp_congestion_ops *tcp_ca_find(const char *name)
|
|
{
|
|
struct tcp_congestion_ops *e;
|
|
|
|
list_for_each_entry_rcu(e, &tcp_cong_list, list) {
|
|
if (strcmp(e->name, name) == 0)
|
|
return e;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/* Must be called with rcu lock held */
|
|
static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name)
|
|
{
|
|
const struct tcp_congestion_ops *ca = tcp_ca_find(name);
|
|
#ifdef CONFIG_MODULES
|
|
if (!ca && capable(CAP_NET_ADMIN)) {
|
|
rcu_read_unlock();
|
|
request_module("tcp_%s", name);
|
|
rcu_read_lock();
|
|
ca = tcp_ca_find(name);
|
|
}
|
|
#endif
|
|
return ca;
|
|
}
|
|
|
|
/* Simple linear search, not much in here. */
|
|
struct tcp_congestion_ops *tcp_ca_find_key(u32 key)
|
|
{
|
|
struct tcp_congestion_ops *e;
|
|
|
|
list_for_each_entry_rcu(e, &tcp_cong_list, list) {
|
|
if (e->key == key)
|
|
return e;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Attach new congestion control algorithm to the list
|
|
* of available options.
|
|
*/
|
|
int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
|
|
{
|
|
int ret = 0;
|
|
|
|
/* all algorithms must implement ssthresh and cong_avoid ops */
|
|
if (!ca->ssthresh || !ca->cong_avoid) {
|
|
pr_err("%s does not implement required ops\n", ca->name);
|
|
return -EINVAL;
|
|
}
|
|
|
|
ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name));
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) {
|
|
pr_notice("%s already registered or non-unique key\n",
|
|
ca->name);
|
|
ret = -EEXIST;
|
|
} else {
|
|
list_add_tail_rcu(&ca->list, &tcp_cong_list);
|
|
pr_info("%s registered\n", ca->name);
|
|
}
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_register_congestion_control);
|
|
|
|
/*
|
|
* Remove congestion control algorithm, called from
|
|
* the module's remove function. Module ref counts are used
|
|
* to ensure that this can't be done till all sockets using
|
|
* that method are closed.
|
|
*/
|
|
void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
|
|
{
|
|
spin_lock(&tcp_cong_list_lock);
|
|
list_del_rcu(&ca->list);
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
/* Wait for outstanding readers to complete before the
|
|
* module gets removed entirely.
|
|
*
|
|
* A try_module_get() should fail by now as our module is
|
|
* in "going" state since no refs are held anymore and
|
|
* module_exit() handler being called.
|
|
*/
|
|
synchronize_rcu();
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
|
|
|
|
u32 tcp_ca_get_key_by_name(const char *name)
|
|
{
|
|
const struct tcp_congestion_ops *ca;
|
|
u32 key;
|
|
|
|
might_sleep();
|
|
|
|
rcu_read_lock();
|
|
ca = __tcp_ca_find_autoload(name);
|
|
key = ca ? ca->key : TCP_CA_UNSPEC;
|
|
rcu_read_unlock();
|
|
|
|
return key;
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_ca_get_key_by_name);
|
|
|
|
char *tcp_ca_get_name_by_key(u32 key, char *buffer)
|
|
{
|
|
const struct tcp_congestion_ops *ca;
|
|
char *ret = NULL;
|
|
|
|
rcu_read_lock();
|
|
ca = tcp_ca_find_key(key);
|
|
if (ca)
|
|
ret = strncpy(buffer, ca->name,
|
|
TCP_CA_NAME_MAX);
|
|
rcu_read_unlock();
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key);
|
|
|
|
/* Assign choice of congestion control. */
|
|
void tcp_assign_congestion_control(struct sock *sk)
|
|
{
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
|
|
if (likely(try_module_get(ca->owner))) {
|
|
icsk->icsk_ca_ops = ca;
|
|
goto out;
|
|
}
|
|
/* Fallback to next available. The last really
|
|
* guaranteed fallback is Reno from this list.
|
|
*/
|
|
}
|
|
out:
|
|
rcu_read_unlock();
|
|
|
|
/* Clear out private data before diag gets it and
|
|
* the ca has not been initialized.
|
|
*/
|
|
if (ca->get_info)
|
|
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
|
|
}
|
|
|
|
void tcp_init_congestion_control(struct sock *sk)
|
|
{
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
if (icsk->icsk_ca_ops->init)
|
|
icsk->icsk_ca_ops->init(sk);
|
|
}
|
|
|
|
static void tcp_reinit_congestion_control(struct sock *sk,
|
|
const struct tcp_congestion_ops *ca)
|
|
{
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
tcp_cleanup_congestion_control(sk);
|
|
icsk->icsk_ca_ops = ca;
|
|
|
|
if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
|
|
icsk->icsk_ca_ops->init(sk);
|
|
}
|
|
|
|
/* Manage refcounts on socket close. */
|
|
void tcp_cleanup_congestion_control(struct sock *sk)
|
|
{
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
if (icsk->icsk_ca_ops->release)
|
|
icsk->icsk_ca_ops->release(sk);
|
|
module_put(icsk->icsk_ca_ops->owner);
|
|
}
|
|
|
|
/* Used by sysctl to change default congestion control */
|
|
int tcp_set_default_congestion_control(const char *name)
|
|
{
|
|
struct tcp_congestion_ops *ca;
|
|
int ret = -ENOENT;
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
ca = tcp_ca_find(name);
|
|
#ifdef CONFIG_MODULES
|
|
if (!ca && capable(CAP_NET_ADMIN)) {
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
request_module("tcp_%s", name);
|
|
spin_lock(&tcp_cong_list_lock);
|
|
ca = tcp_ca_find(name);
|
|
}
|
|
#endif
|
|
|
|
if (ca) {
|
|
ca->flags |= TCP_CONG_NON_RESTRICTED; /* default is always allowed */
|
|
list_move(&ca->list, &tcp_cong_list);
|
|
ret = 0;
|
|
}
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/* Set default value from kernel configuration at bootup */
|
|
static int __init tcp_congestion_default(void)
|
|
{
|
|
return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
|
|
}
|
|
late_initcall(tcp_congestion_default);
|
|
|
|
/* Build string with list of available congestion control values */
|
|
void tcp_get_available_congestion_control(char *buf, size_t maxlen)
|
|
{
|
|
struct tcp_congestion_ops *ca;
|
|
size_t offs = 0;
|
|
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
|
|
offs += snprintf(buf + offs, maxlen - offs,
|
|
"%s%s",
|
|
offs == 0 ? "" : " ", ca->name);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* Get current default congestion control */
|
|
void tcp_get_default_congestion_control(char *name)
|
|
{
|
|
struct tcp_congestion_ops *ca;
|
|
/* We will always have reno... */
|
|
BUG_ON(list_empty(&tcp_cong_list));
|
|
|
|
rcu_read_lock();
|
|
ca = list_entry(tcp_cong_list.next, struct tcp_congestion_ops, list);
|
|
strncpy(name, ca->name, TCP_CA_NAME_MAX);
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* Built list of non-restricted congestion control values */
|
|
void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
|
|
{
|
|
struct tcp_congestion_ops *ca;
|
|
size_t offs = 0;
|
|
|
|
*buf = '\0';
|
|
rcu_read_lock();
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
|
|
if (!(ca->flags & TCP_CONG_NON_RESTRICTED))
|
|
continue;
|
|
offs += snprintf(buf + offs, maxlen - offs,
|
|
"%s%s",
|
|
offs == 0 ? "" : " ", ca->name);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* Change list of non-restricted congestion control */
|
|
int tcp_set_allowed_congestion_control(char *val)
|
|
{
|
|
struct tcp_congestion_ops *ca;
|
|
char *saved_clone, *clone, *name;
|
|
int ret = 0;
|
|
|
|
saved_clone = clone = kstrdup(val, GFP_USER);
|
|
if (!clone)
|
|
return -ENOMEM;
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
/* pass 1 check for bad entries */
|
|
while ((name = strsep(&clone, " ")) && *name) {
|
|
ca = tcp_ca_find(name);
|
|
if (!ca) {
|
|
ret = -ENOENT;
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/* pass 2 clear old values */
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list)
|
|
ca->flags &= ~TCP_CONG_NON_RESTRICTED;
|
|
|
|
/* pass 3 mark as allowed */
|
|
while ((name = strsep(&val, " ")) && *name) {
|
|
ca = tcp_ca_find(name);
|
|
WARN_ON(!ca);
|
|
if (ca)
|
|
ca->flags |= TCP_CONG_NON_RESTRICTED;
|
|
}
|
|
out:
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
kfree(saved_clone);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/* Change congestion control for socket */
|
|
int tcp_set_congestion_control(struct sock *sk, const char *name)
|
|
{
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
const struct tcp_congestion_ops *ca;
|
|
int err = 0;
|
|
|
|
if (icsk->icsk_ca_dst_locked)
|
|
return -EPERM;
|
|
|
|
rcu_read_lock();
|
|
ca = __tcp_ca_find_autoload(name);
|
|
/* No change asking for existing value */
|
|
if (ca == icsk->icsk_ca_ops)
|
|
goto out;
|
|
if (!ca)
|
|
err = -ENOENT;
|
|
else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
|
|
ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)))
|
|
err = -EPERM;
|
|
else if (!try_module_get(ca->owner))
|
|
err = -EBUSY;
|
|
else
|
|
tcp_reinit_congestion_control(sk, ca);
|
|
out:
|
|
rcu_read_unlock();
|
|
return err;
|
|
}
|
|
|
|
/* Slow start is used when congestion window is no greater than the slow start
|
|
* threshold. We base on RFC2581 and also handle stretch ACKs properly.
|
|
* We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but
|
|
* something better;) a packet is only considered (s)acked in its entirety to
|
|
* defend the ACK attacks described in the RFC. Slow start processes a stretch
|
|
* ACK of degree N as if N acks of degree 1 are received back to back except
|
|
* ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
|
|
* returns the leftover acks to adjust cwnd in congestion avoidance mode.
|
|
*/
|
|
void tcp_slow_start(struct tcp_sock *tp, u32 acked)
|
|
{
|
|
u32 cwnd = tp->snd_cwnd + acked;
|
|
|
|
if (cwnd > tp->snd_ssthresh)
|
|
cwnd = tp->snd_ssthresh + 1;
|
|
tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_slow_start);
|
|
|
|
/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
|
|
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
|
|
{
|
|
if (tp->snd_cwnd_cnt >= w) {
|
|
if (tp->snd_cwnd < tp->snd_cwnd_clamp)
|
|
tp->snd_cwnd++;
|
|
tp->snd_cwnd_cnt = 0;
|
|
} else {
|
|
tp->snd_cwnd_cnt++;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
|
|
|
|
/*
|
|
* TCP Reno congestion control
|
|
* This is special case used for fallback as well.
|
|
*/
|
|
/* This is Jacobson's slow start and congestion avoidance.
|
|
* SIGCOMM '88, p. 328.
|
|
*/
|
|
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
|
|
{
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
if (!tcp_is_cwnd_limited(sk))
|
|
return;
|
|
|
|
/* In "safe" area, increase. */
|
|
if (tp->snd_cwnd <= tp->snd_ssthresh)
|
|
tcp_slow_start(tp, acked);
|
|
/* In dangerous area, increase slowly. */
|
|
else
|
|
tcp_cong_avoid_ai(tp, tp->snd_cwnd);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
|
|
|
|
/* Slow start threshold is half the congestion window (min 2) */
|
|
u32 tcp_reno_ssthresh(struct sock *sk)
|
|
{
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
return max(tp->snd_cwnd >> 1U, 2U);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
|
|
|
|
struct tcp_congestion_ops tcp_reno = {
|
|
.flags = TCP_CONG_NON_RESTRICTED,
|
|
.name = "reno",
|
|
.owner = THIS_MODULE,
|
|
.ssthresh = tcp_reno_ssthresh,
|
|
.cong_avoid = tcp_reno_cong_avoid,
|
|
};
|